This is the MATLAB implementation of the Movement Feature Space (MFS) proposed in the papers [1,2,3].
This code shows how the level lines and the adaptative background reference are calculated.
I provide an intersection video sequence to test the code.
If you use this code, please give appropiate acknowledgements:
[1] P. Negri, "Estimating the queue length at street intersections by using a movement feature space approach", IET Image Processing, vol. 8, issue 7, pages 406–416, July 2014.
[2] P. Negri, N. Goussies, P. Lotito, "Detecting pedestrians on a Movement Feature Space", vol. 47, issue 1, pages 56-71, January 2014.
[3] P. Negri, P. Lotito, "Pedestrian Detection Using a Feature Space Based on Colored Level Lines", Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications,
Lecture Notes in Computer Science, Volume 7441/2012, Pages 885-892, 2012 (Best Paper Award).
Links:
code download (3 KB)
video sequence download (25.3 MB)
